Office of Technology Transfer – University of Michigan

Perimetric Testing for Evaluation of Patients with Glaucoma and Suspected Glaucoma

Technology #5140

Questions about this technology? Ask a Technology Manager

Download Printable PDF

Joshua D. Stein
Managed By
Drew Bennett
Associate Director - Software Licensing 734-615-4004
Patent Protection
US Patent Pending


2.2 million Americans have glaucoma, and this number is expected to grow to over 3 million by 2020. Glaucoma can be managed and its progression slowed, provided clinicians are able to monitor disease progression at appropriate intervals and tailor treatment plans accordingly. In glaucoma, as is the case with various chronic diseases, clinicians face the problem of interpreting multidimensional data to make decisions for treating their patients. As a result, clinicians often defer to standardized schedules of testing and monitoring of disease progress. Standard interval monitoring plans ignore the individual characteristics of a give patient’s disease, and therefore often fail to provide an optimal testing schedule for the patient. Decision support systems can aid the clinician in interpreting clinical data to develop and appropriate course of action for a given patient.


Researchers at the University of Michigan have developed an algorithm for determining the optimal testing schedule for monitoring the disease progression of a given patient. By taking into account dynamic disease evolution in a feedback-driven forecasting and control algorithm, this technology significantly advances the state-of-the-art in modeling of chronic disease and monitoring of disease progression. In experiments using data from large-scale glaucoma clinical trials (CIGTS data) this algorithm outperformed fixed interval testing regimens, which are the current clinical standard. The algorithm predicted testing intervals which better captured disease progression, requiring fewer tests overall to do so. Employment of this algorithm as a physician decision support system can increase efficiency and patient care in the management of chronic diseases.

Applications and Advantages


  • Dynamic modeling of chronic disease progression
  • Algorithm for determining optimal time for next diagnostic test to monitor chronic disease progression


  • Incorporates dynamic updating of information
  • Improves efficiency of patient testing, reducing costs and improving quality of care
  • Can be incorporated into preexisting software associated with testing apparatus